© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7208
    Prev
    Next
    INDEX
    Explanations

    strings of two or three characters, especially "az" and "baz"

    oai_token-act-pair · gemini-2.0-flash

    specific proper nouns or placeholders

    np_token-act-pair-logits · gpt-4o-mini

    Contains "az" prefixes/suffixes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.64
    aspectj
    -0.52
     Réponses
    -0.51
    ClientSize
    -0.51
    /******/
    -0.49
    openConnection
    -0.48
    ::::::::
    -0.47
    AutoresizingMask
    -0.46
    INCREF
    -0.46
    sela
    -0.46
    POSITIVE LOGITS
     мәкал
    0.69
    kheim
    0.58
    
    0.57
    ustimmung
    0.54
     probado
    0.54
    pence
    0.54
     tanong
    0.53
     TAMBÉM
    0.53
     AspNetCore
    0.50
     getRule
    0.50
    Activations Density 0.439%

    No Known Activations